João Pedro SantosA leap into NLP: Text2Gloss translation with transformersIn my last post, I went over how I trained an AI to recognize four signs from Argentinian Sign Language through video. Now I’m here to show…Feb 9Feb 9
InLevel Up CodingbyDr. Ashish BamaniaDeepSeek-R1 Beats OpenAI’s o1, Revealing All Its Training Secrets Out In The OpenA deep dive into how DeepSeek-R1 was trained from scratch and how this open-source research will accelerate AI progress like never before.Jan 2732Jan 2732
InLevel Up CodingbyDr. Ashish BamaniaReinforcement Learning From Human Feedback (RLHF) Doesn’t Need To Be Complex AnymoreA deep dive into training an LLM and using Reinforcement Learning from Human Feedback (RLHF) with PPO to align it with human values.Nov 25, 2024Nov 25, 2024
